Intelligent security inspection method and system

Abstract

The present invention provides an intelligent security inspection method and system, which relates to the field of intelligent security inspection. The method comprises: obtaining the detection time of the security inspection of the i-th person carrying the items, and obtaining the image to be inspected through an X-ray machine; determining the suspected prohibited items, and obtaining the real image of the suspected prohibited items, determining the category feature information, size information and quantity of the suspected prohibited items, so as to judge whether the suspected prohibited items are prohibited items, and if so, determining the comprehensive risk coefficient and determining the disposal method. According to the present invention, whether the suspected prohibited items are prohibited items is determined based on parameters such as the category feature information, size information and quantity of the suspected prohibited items, which reduces the possibility of misjudgment, and the comprehensive risk coefficient of all prohibited items carried by the person carrying the items can be determined, so as to determine the disposal method, thereby improving the comprehensiveness and accuracy of the security inspection and reducing safety hazards.

Description

Technical Field

[0001] The present invention relates to the field of intelligent security inspection, and in particular to an intelligent security inspection method and system. Background Art

[0002] In the related art, CN115186949A provides a railway passenger station security centralized management method, equipment and medium, which are applied to the railway passenger station security centralized management system, which includes centralized storage service, centralized image judgment service and centralized analysis service, including: inputting the original X-ray image data into the centralized analysis service, so that the centralized analysis service analyzes and processes the original X-ray image data based on the recognition model to obtain the centralized analysis result; inputting the original X-ray image data into the image judgment equipment in the centralized image judgment room corresponding to the centralized image judgment service, so that the image judges in the centralized image judgment room can perform real-time image judgment and obtain manual analysis results; converting the original X-ray image data into security inspection X-ray images, and inputting the security inspection X-ray images into the centralized storage service to realize the later traceability and search. The invention is used to solve the defects of insufficient information level of the security inspection system and poor overall security inspection quality, realize the informatization of the railway security inspection system, and improve the quality of security inspection.

[0003] CN115169806A provides a scheduling method, device, system and readable storage medium for security inspection image judgment, wherein the scheduling method for security inspection image judgment includes obtaining image judgment tasks, wherein the image judgment task is a task of identifying restricted items based on the image generated when the security inspection instrument scans the item; assigning the image judgment task to the image judgment terminal with the highest priority; wherein the priority of the image judgment terminal is negatively correlated with the number of image judgment tasks to be processed by itself; obtaining the image judgment result returned by the image judgment terminal, and sending the image judgment result to the disposal terminal. The method of the invention can perform real-time scheduling of the image judgment tasks generated by the security inspection instrument, assign the image judgment tasks to suitable and idle image judgment terminals, reduce the waiting time of passengers as much as possible, and reduce the number of check-in staff without affecting the travel experience of passengers, thereby improving the efficiency of railway security inspection.

[0004] According to the relevant technology, manual security inspection and automatic security inspection can be combined to improve the efficiency of security inspection of items carried by passengers. However, the relevant technology does not consider the situation where a person carries multiple prohibited items, nor does it verify the actual danger of the items in the image to be inspected identified by the X-ray machine. For example, the X-ray machine can only determine the outline shape of the item, but if an item is only a non-prohibited item with a shape similar to a prohibited item, it is easy to make a misjudgment.

[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides an intelligent security inspection method and system, which can solve the technical problem of misjudgment in security inspection of carrying prohibited items.

[0007] According to a first aspect of the present invention, there is provided an intelligent security inspection method, comprising:

[0008] Get the detection time of the i-th person carrying security check, where i is a positive integer;

[0009] Obtain images of items to be inspected through an X-ray machine;

[0010] If it is determined that there are suspected prohibited items in the image to be inspected of the i-th person carrying the bag, the bag is opened for inspection and the real image of the suspected prohibited items is obtained through the camera;

[0011] Determining, by means of an image recognition model, category feature information of suspected prohibited items in the real image and size information of the suspected prohibited items;

[0012] Determining whether the suspected prohibited items are prohibited items based on the category feature information, size information and quantity of the suspected prohibited items;

[0013] If the suspected prohibited item is a prohibited item, determining the comprehensive risk factor of all prohibited items carried by the i-th carrier according to the category feature information, size information and quantity of the prohibited items;

[0014] Get the identity information of the i-th person;

[0015] The disposal method is determined based on the identity information and the comprehensive risk factor.

[0016] According to a second aspect of the present invention, there is provided an intelligent security inspection system, comprising:

[0017] cameras, ID card readers, printers, lockers and processors;

[0018] The processor is used to:

[0019] Get the detection time of the i-th person carrying security check, where i is a positive integer;

[0020] Obtain images of items to be inspected through an X-ray machine;

[0021] If it is determined that there are suspected prohibited items in the image to be inspected of the i-th person carrying the bag, the bag is opened for inspection and the real image of the suspected prohibited items is obtained through the camera;

[0022] Determining, by means of an image recognition model, category feature information of suspected prohibited items in the real image and size information of the suspected prohibited items;

[0023] Determining whether the suspected prohibited items are prohibited items based on the category feature information, size information and quantity of the suspected prohibited items;

[0024] If the suspected prohibited item is a prohibited item, determining the comprehensive risk factor of all prohibited items carried by the i-th carrier according to the category feature information, size information and quantity of the prohibited items;

[0025] Obtain the identity information of the i-th person through the ID card reader;

[0026] Determine a disposal method based on the identity information and the comprehensive risk factor;

[0027] The disposal methods include:

[0028] If the comprehensive risk factor is lower than or equal to a first threshold, the identity information, the category feature information of the prohibited item and the real image are saved;

[0029] If the comprehensive risk factor is higher than the first threshold and lower than or equal to the second threshold, the prohibited items are temporarily stored in a locker, a temporary storage certificate is generated according to the identity information, and the temporary storage certificate is printed by a printer, and the second threshold is higher than the first threshold;

[0030] If the comprehensive risk factor is higher than a second threshold, the prohibited items are stored in a locker and a prompt message is generated, wherein the prompt message is used to prompt the staff to call the police.

[0031] Technical effect: According to the present invention, after the suspected prohibited items are identified by the X-ray machine, the real image can be obtained by the camera, and the suspected prohibited items can be determined whether they are prohibited items according to the category feature information, size information and quantity of the suspected prohibited items, thereby reducing the possibility of misjudgment. In addition, the comprehensive risk coefficient of all prohibited items carried by the carrier can be determined, so as to determine the disposal method, thereby improving the comprehensiveness and accuracy of security inspection and reducing safety hazards. When determining the comprehensive risk coefficient, the danger of the items carried by the carrier can be determined from multiple aspects such as cutting tools, dangerous solids, dangerous powders, dangerous liquids or dangerous gases and radioactive materials, and then the comprehensive risk coefficient of all prohibited items carried by the carrier can be determined, thereby improving the accuracy and objectivity of the comprehensive risk coefficient. Provide basic data for determining the disposal method or generating alarm information. When disposing of prohibited items, the disposal method can be determined according to the comprehensive risk coefficient. If the disposal method is temporary storage, the prohibited items can be temporarily stored in a suitable locker, and the first facial feature information and the first signature image of the carrier can be obtained, so as to generate a temporary storage voucher printed with a pickup identification code. When picking up the item, the recipient scans the pickup identification code and compares the second facial feature information of the recipient with the first facial feature information to determine whether the person carrying the item is picking up the item. If the person carrying the item is picking up the item, the cabinet door is opened. If the person carrying the item is not picking up the item, the second signature image in the image of the authorization document signed by the person carrying the item held by the recipient can be photographed, and the first signature feature information and the second signature feature information can be compared to determine whether the authorization document can be used to pick up the item, thereby improving the accuracy and comprehensiveness of security checks, and improving the convenience and safety of storing and retrieving items. When checking gang members, the time interval for checking can be determined based on the consistency of the gang members' travel time, and suspected gang members can be identified based on the consistency of the prohibited items carried by the gang members and the consistency of the dangerousness, thereby improving the accuracy of checking gang members, and then gang record information can be generated for easy inspection, improving the comprehensiveness and accuracy of security checks.

[0032] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work.

[0034] Figure 1A schematic diagram of a process flow of an intelligent security inspection method according to an embodiment of the present invention is exemplarily shown;

[0035] Figure 2 A schematic diagram of an intelligent security inspection system according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0038] Figure 1 A flowchart of an intelligent security inspection method according to an embodiment of the present invention is exemplarily shown, and the method includes:

[0039] Step S101, obtaining the detection time of the i-th person carrying a security check, where i is a positive integer;

[0040] Step S102, obtaining an image of the object to be inspected by an X-ray machine;

[0041] Step S103, if it is determined that there are suspected prohibited items in the image to be inspected of the i-th person carrying the bag, the bag is opened for inspection and a real image of the suspected prohibited items is obtained through a camera;

[0042] Step S104, determining the category feature information of the suspected prohibited items in the real image and the size information of the suspected prohibited items through the image recognition model;

[0043] Step S105, judging whether the suspected prohibited item is a prohibited item according to the category feature information, size information and quantity of the suspected prohibited item;

[0044] Step S106, if the suspected prohibited item is a prohibited item, determining the comprehensive risk factor of all prohibited items carried by the i-th carrier according to the category feature information, size information and quantity of the prohibited items;

[0045] Step S107, obtaining the identity information of the i-th person carrying the vehicle;

[0046] Step S108, determining a handling method based on the identity information and the comprehensive risk factor.

[0047] According to the intelligent security inspection method of the present invention, after the suspected prohibited items are identified by the X-ray machine, the real image can be obtained by the camera, and the suspected prohibited items can be determined whether they are prohibited items according to the category feature information, size information and quantity parameters of the suspected prohibited items, thereby reducing the possibility of misjudgment. In addition, the comprehensive risk factor of all prohibited items carried by the carrier can be determined, so as to determine the disposal method, thereby improving the comprehensiveness and accuracy of security inspection and reducing safety hazards.

[0048] According to an embodiment of the present invention, in step S101, the detection time of the security check of the i-th person carrying the vehicle is obtained, where i is a positive integer. For example, if the time when the i-th person carrying the vehicle passes through the gate for security check is 15:30, then the detection time of the security check of the i-th person carrying the vehicle is 15:30.

[0049] According to an embodiment of the present invention, in step S102, when the items carried by the i-th person pass through security inspection equipment such as an X-ray security inspection machine, an image to be inspected may be captured, and the image to be inspected is an X-ray image, which can be used to identify the contour information of the item. If suspected contraband items are found based on the contour information, the package may be opened for inspection in step S103. For example, suspected contraband items may include batteries exceeding the specified capacity, cosmetics, cutting tools, flammable and explosive items, etc.

[0050] According to an embodiment of the present invention, in step S103, during the process of opening the package for inspection, the item with the outline information of the suspected prohibited item may be photographed by a camera to obtain a real image of the suspected prohibited item.

[0051] According to an embodiment of the present invention, in step S104, the category feature information of the prohibited items in the real image and the size information of the prohibited items are determined by an image recognition model. For example, a deep learning neural network model can be used to determine the category feature information of the prohibited items in the image to be inspected, thereby helping to classify the prohibited items. The category feature information can be information in the form of a vector, and the value of the element in the vector can be used to describe the category to which the prohibited items belong. The present invention does not limit the form of the category feature information. The size information of the suspected prohibited items can also be determined by parsing the image to be inspected, such as the length of a cutting tool, the volume of a container containing flammable and explosive items, etc.

[0052] According to an embodiment of the present invention, in step S105, it is possible to determine whether the suspected prohibited item is a prohibited item based on the category feature information, size information and quantity of the suspected prohibited item. For example, if the category feature information of the suspected prohibited item indicates that the suspected prohibited item is a toy knife, not a dangerous blade, then the suspected prohibited item is not a prohibited item. For another example, based on the size information of the suspected prohibited item, it can be determined that the container containing cosmetics is likely to exceed the regulations, and the suspected prohibited item is determined to be a prohibited item.

[0053] According to an embodiment of the present invention, in step S106, if the suspected prohibited item is a prohibited item, the comprehensive risk coefficient of all prohibited items carried by the i-th carrier is determined based on the category characteristic information, size information and quantity of the prohibited item, including: determining the risk weight corresponding to the category of the j-th prohibited item based on the category characteristic information of the j-th prohibited item of the i-th carrier; determining the comprehensive risk coefficient of all prohibited items carried by the i-th carrier based on the risk weight, the size information and the quantity.

[0054] According to an embodiment of the present invention, the risk weight corresponding to the category of the j-th prohibited item of the i-th carrier is determined based on the category feature information of the j-th prohibited item of the i-th carrier. For dangerous goods of different categories, their corresponding risk weights are determined according to different degrees of risk. For example, different risk weights are preset for batteries, cosmetics, cutting tools, flammable and explosive items that exceed the specified capacity, and the larger the risk weight, the higher the risk of the corresponding prohibited item. In addition, the number of the dangerous goods can be determined. In theory, the more the number of dangerous goods, the higher the risk of the carrier. Furthermore, the larger the size of the prohibited item, the higher the risk. For example, the larger the volume of the container for the prohibited items, the more the number of prohibited items contained, and the higher the risk.

[0055] According to an embodiment of the present invention, the comprehensive risk coefficient of all prohibited items carried by the i-th carrier is determined according to the risk weight, the size information and the quantity, including: determining whether the prohibited items include cutting tools according to the category characteristic information; if the prohibited items include cutting tools, obtaining the length of the cutting tools according to the size information of the cutting tools; determining whether the prohibited items include dangerous goods containers according to the category characteristic information; if the prohibited items include dangerous goods containers, determining whether the dangerous goods containers contain dangerous solids, dangerous powders, dangerous liquids or dangerous gases through a detector, and determining the concentration of the dangerous gases; obtaining the capacity of the dangerous goods containers according to the size information of the dangerous goods containers; determining whether there are radioactive substances in the items through a radiation detector; if there are radioactive substances, determining the radiation dose of the radioactive substances; determining the comprehensive risk coefficient of all prohibited items carried by the i-th carrier according to the number and length of the cutting tools, the number and capacity of dangerous goods containers containing dangerous solids, dangerous powders, dangerous liquids or dangerous gases, and the concentration of dangerous gases or dangerous liquids, as well as the number and radiation dose of the radioactive substances.

[0056] According to an embodiment of the present invention, if the prohibited items of the i-th person carrying the goods include a cutting tool, the length of the cutting tool is obtained according to the size information of the cutting tool. In theory, the longer the length of the cutting tool, the higher the danger of the dangerous goods.

[0057] According to an embodiment of the present invention, if the prohibited items of the i-th person carrying the dangerous goods container include a dangerous goods container, then the detector is used to determine whether the dangerous goods container contains dangerous solids, dangerous powders, dangerous liquids or dangerous gases, etc. If the dangerous goods container contains dangerous liquids or dangerous gases, the concentration of the dangerous liquids or gases can be determined. For example, a handheld liquid detector can be used to determine whether a dangerous goods container contains flammable, explosive, corrosive or toxic liquids. A gas detector is used to determine whether a dangerous goods container contains flammable, explosive or toxic gases. Further, the concentration of the dangerous liquid or gas can also be estimated by the above-mentioned instrument. In theory, the higher the concentration of the dangerous liquid or gas of the same volume, the higher the danger of the dangerous goods. The capacity of the dangerous goods container is obtained according to the size information of the dangerous goods container. In theory, for dangerous goods of the same concentration or density, the larger the capacity of the dangerous goods container, the higher the danger of the dangerous goods.

[0058] According to an embodiment of the present invention, if the radiation detector determines that there are radioactive objects in the items of the i-th person, the radiation dose of the radioactive objects is determined. In theory, the greater the radiation dose of the radioactive objects, the higher the danger of the dangerous goods.

[0059] According to an embodiment of the present invention, the number and capacity of dangerous goods containers storing dangerous solids, dangerous powders, dangerous liquids or dangerous gases, the concentration of dangerous gases or dangerous liquids, and the number and radiation dose of radioactive materials are used to determine the comprehensive risk factor of all prohibited items carried by the i-th carrier, including: determining the comprehensive risk factor D of all prohibited items carried by the i-th carrier according to formula (1): i ,

[0060]

[0061] Among them, α i,j is the risk weight of the jth cutting tool of the i-th person carrying the tool, L i,j is the length of the jth blade of the i-th person carrying the i is the number of cutting tools of the i-th person carrying the knife, α i,k is the hazard weight of the kth hazardous container containing hazardous liquid or gas for the i-th person, V i,k is the volume of the kth dangerous goods container carrying the i-th person, C i,k is the concentration of dangerous liquid or gas in the kth dangerous goods container carrying the i-th person, m i is the number of dangerous goods containers containing dangerous liquids or gases for the i-th person carrying the dangerous goods, α i,s is the risk weight of the sth radiation of the ith person, D i,s is the radiation dose of the sth radiation object carrying the ith person, h i is the number of radioactive materials carrying the i-th person, j≤n i , k≤m i ,s≤h i , and j, k, s, n i 、m i and h i All are positive integers.

[0062] According to an embodiment of the present invention, the formula (1) includes the risk α of the jth cutting tool of the i-th person carrying the tool. i, j L i,j Since the longer the length of the cutting tool is, the more dangerous the cutting tool is, the dangerousness weight can be multiplied by the length of the j-th cutting tool to obtain the dangerousness of the j-th cutting tool. It can be expressed as the weighted sum of the lengths of all the cutting tools carried by the ith carrier to obtain the danger of the cutting tools carried by the ith carrier. Similarly, since the larger the capacity of the container of dangerous liquid or gas, the higher the concentration of the dangerous liquid or gas, the higher the danger, therefore, α i,k V i,k C i,kIt can represent the danger of the dangerous liquid or gas contained in the kth dangerous goods container carried by the i-th carrier. If the dangerous goods container contains dangerous solids or dangerous powders, the concentration can be set to 1. It can be expressed as the weighted sum of the volume and concentration of all dangerous solids, dangerous powders, dangerous liquids or dangerous gases carried by the ith carrier, and the dangerousness of the dangerous solids, dangerous powders, dangerous liquids or dangerous gases carried by the ith carrier is obtained. Similarly, since the greater the dose of the radiation, the higher the danger of the radiation, therefore, α i,s D i,s is the danger of the sth radiation carried by the ith carrier, The weighted sum of the doses of all the radiations carried by the ith carrier can be expressed to obtain the danger of the radiations carried by the ith carrier. Thus, the comprehensive danger coefficient of all the prohibited items carried by the ith carrier is determined according to the sum of the danger of the cutting tools carried by the ith carrier, the danger of the dangerous solids, dangerous powders, dangerous liquids or dangerous gases carried, and the danger of the radiations carried. The greater the comprehensive danger coefficient, the higher the danger of all the prohibited items carried by the carrier, and vice versa, the smaller the comprehensive danger coefficient, the lower the danger of all the prohibited items carried by the carrier.

[0063] In this way, the danger of the items carried by the carrier can be determined from multiple aspects such as cutting tools, dangerous solids, dangerous powders, dangerous liquids or dangerous gases and radioactive materials, and then the comprehensive danger coefficient of all prohibited items carried by the carrier can be determined, thereby improving the accuracy and objectivity of the comprehensive danger coefficient. It provides basic data for determining the disposal method or generating alarm information.

[0064] According to an embodiment of the present invention, in step S107, the identity card of the i-th carrier may be read by an identity card reader to obtain the identity information of the i-th carrier.

[0065] According to an embodiment of the present invention, in step S108, a disposal method is determined based on the identity information and the comprehensive risk coefficient, including: if the comprehensive risk coefficient is lower than or equal to a first threshold, the identity information, the category characteristic information and the real image of the prohibited item are saved; if the comprehensive risk coefficient is higher than the first threshold and lower than or equal to a second threshold, the prohibited item is temporarily stored in a locker, and a temporary storage certificate is generated based on the identity information, and the second threshold is higher than the first threshold; if the comprehensive risk coefficient is higher than the second threshold, the prohibited item is stored in a locker, and a prompt message is generated, wherein the prompt message is used to prompt the staff to call the police.

[0066] According to an embodiment of the present invention, if the comprehensive risk coefficient is higher than a first threshold value and lower than or equal to a second threshold value, the prohibited items are temporarily stored in a locker, and a temporary storage certificate is generated based on the identity information, including: obtaining the identity information of the carrier, and obtaining the facial image and the first signature image of the carrier; determining a locker for temporarily storing the prohibited items based on the size information and the quantity of the prohibited items, and opening the locker; after the prohibited items are stored in the locker, closing the locker, generating a pickup code, and printing a temporary storage certificate, the content of the temporary storage certificate including the pickup code and the pickup time limit, after which the pickup code becomes invalid.

[0067] For example, the carrier may be carrying batteries exceeding the specified capacity or alcohol-containing cosmetics and other low-risk items. The identity information, facial image and first signature image of the carrier are recorded, that is, the identity information, facial image and signature image of the carrier are used to identify the pickup. According to the size information and quantity of the prohibited items, a locker that is sufficient to accommodate all the prohibited items carried by the carrier is opened. After the prohibited items are placed in the locker, the locker is closed and a temporary voucher with a pickup identification code is printed. After scanning the pickup identification code, the identity information, facial image, first signature image and other information of the carrier can be retrieved from the database. For example, the identification code is a QR code or a bar code, etc., which is used for the carrier to pick up the item. In addition, the content of the temporary voucher also includes a collection time limit, prompting the above-mentioned carrier to collect it before the collection time limit.

[0068] According to an embodiment of the present invention, the method also includes: scanning the pickup identification code of the temporary storage voucher and obtaining the pickup time limit; if the current date is before the pickup time limit, photographing the facial image of the recipient; obtaining the first facial feature information of the facial image of the carrier and the second facial feature information of the facial image of the recipient; if the similarity between the first facial feature information and the second facial feature information is greater than or equal to a preset facial similarity threshold, opening the locker; if the similarity between the first facial feature information and the second facial feature information is less than the preset facial similarity threshold, photographing an image of the entrusted pickup document with the signature of the carrier, and intercepting a second signature image at a preset position in the image of the entrusted pickup document; obtaining the first signature feature information of the first signature image and the second signature feature information of the second signature image; if the first signature feature information and the second signature feature information are greater than or equal to the preset signature similarity threshold, opening the locker.

[0069] According to an embodiment of the present invention, if the current date has exceeded the collection time limit, the staff can be prompted to discard the items temporarily stored in the locker. If the current date is before the collection time limit and the recipient scans the temporary storage voucher, the facial image of the recipient can be captured by the camera. And through the face recognition system, the second facial feature information of the facial image of the recipient and the facial image of the carrier retrieved by scanning the collection identification code are obtained, and then the first facial feature information is obtained. The similarity between the first facial feature information and the second facial feature information is compared by the preset algorithm of the locker, for example, the similarity between the first facial feature information and the second facial feature information is compared by using a deep learning neural network model. And according to the preset facial similarity threshold, it is determined whether the carrier himself picks up the item. If the similarity is greater than or equal to the preset facial similarity threshold, that is, the carrier and the recipient are the same person, then the locker is opened. On the contrary, if the similarity is less than the preset facial similarity threshold, that is, the carrier and the recipient are not the same person, the carrier may entrust someone else to pick up the item, and further identification is required.

[0070] According to an embodiment of the present invention, the locker needs to take an image of the entrusted pickup document with the signature of the carrier held by the agent, and intercept the second signature image at a preset position in the image of the entrusted pickup document. Similarly, the similarity between the first signature image and the second signature image is compared using the preset algorithm of the locker. And according to the preset signature similarity threshold, it is judged whether the entrusted pickup document held by the agent can prove that the agent is entrusted by the carrier to pick up the item. If the similarity is greater than or equal to the preset signature similarity threshold, that is, the signature of the carrier and the signature in the entrusted pickup document provided by the agent are signed by the same person, then the locker is opened. On the contrary, if the similarity is less than the preset signature similarity threshold, that is, the signature of the carrier and the signature in the entrusted pickup document provided by the agent are not signed by the same person, the entrusted pickup document provided by the agent is invalid and the item cannot be picked up.

[0071] According to the embodiment of the present invention, if the comprehensive risk factor is lower than or equal to the first threshold, that is, the risk of the prohibited items is low, they can be directly released, and the identity information, the category feature information and the real image of the prohibited items are saved for inspection. If the comprehensive risk factor is higher than the second threshold, after the prohibited items are stored in the locker, no temporary storage certificate is generated, but a prompt message is generated to prompt the staff to report the incident through the alarm device, and the prohibited items in the locker are no longer returned to the person carrying them, but handed over to the police.

[0072] In this way, the disposal method can be determined according to the comprehensive risk factor. If the disposal method is temporary storage, the prohibited items can be temporarily stored in a suitable locker, and the first facial feature information and the first signature image of the carrier can be obtained to generate a temporary storage voucher printed with a pickup identification code. When picking up the item, the pick-up person scans the pickup identification code and compares the second facial feature information of the pick-up person with the first facial feature information to determine whether the pick-up person is the person picking up the item. If the pick-up person is the person picking up the item, the cabinet door is opened. If the pick-up person is not the person picking up the item, the second signature image in the image of the entrustment document signed by the carrier held by the pick-up person can be photographed, and the first signature feature information and the second signature feature information can be compared to determine whether the entrustment document can be used to pick up the item, thereby improving the accuracy and comprehensiveness of security inspection, and improving the convenience and safety of storage and retrieval.

[0073] According to an embodiment of the present invention, the method further comprises: if the risk factor is greater than or equal to a preset risk threshold, determining the investigation time interval according to formula (2):

[0074] [t c,i -ε(t d -t c,i ),t c,i +ε(t d -t c,i )](2)

[0075] Among them, t c,i is the detection time of the security check of the i-th person, t d is the departure time of the transportation vehicle, and ε is a preset coefficient less than 1; within the screening time interval, a plurality of suspected gang members are determined whose travel information is consistent with that of the ith carrier; the comprehensive risk coefficient of all prohibited items carried by the suspected gang members is determined; the gang risk coefficient of the suspected gang members is determined according to the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the ith person to be tested, and the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the suspected gang members; when the gang risk coefficient is greater than or equal to the preset coefficient threshold, the suspected gang member is determined as a gang member; and gang record information is generated according to the category characteristic information of the prohibited items carried by the gang members.

[0076] According to an embodiment of the present invention, formula (2) includes the difference t between the departure time of the vehicle and the detection time of the security check of the i-th person carried. d -t c,i, that is, the time that the i-th person carrying the vehicle stays in the station. Moreover, since the travel time and route of the gang members are consistent, the time when multiple gang members arrive at the station is relatively close, and the time they stay in the station is also relatively close. According to the preset coefficient, the effective screening time ε(t d -t c,i ), so t c,i -ε(t d -t c,i ) can represent the time of screening before the detection of the i-th person. Similarly, t c,i +ε(t d -t c,i ) can represent the time of screening after the detection time of the i-th person, and then the screening time interval [t c,i -ε(t d -t c,i ),t c,i +ε(t d -t c,i )], that is, gang members enter the site within this time interval and can be screened based on this time interval.

[0077] According to an embodiment of the present invention, multiple suspected gang members consistent with the travel information of the i-th person carrying the vehicle are determined within the screening time interval. For example, based on the screening time interval, multiple suspected gang members whose security inspection detection time is within the screening time interval and consistent with the travel information of the i-th person carrying the vehicle are determined, that is, multiple suspected gang members consistent with the i-th person carrying the vehicle's travel destination, train number, etc., and the category feature information, risk weight, and comprehensive risk coefficient of the prohibited items carried by the suspected gang members are determined. For example, the comprehensive risk coefficient of all prohibited items carried by the suspected gang members can be determined according to formula (1).

[0078] According to an embodiment of the present invention, the gang risk coefficient of the suspected gang member is determined according to the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the i-th person to be tested, and the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the suspected gang member, including: determining the gang risk coefficient G of the suspected gang member according to formula (3): x ,

[0079]

[0080] Among them, α x,； is the risk weight of the yth prohibited item of the xth suspected gang member, I x,； is the category feature information of the yth prohibited item of the xth suspected gang member, α i,＝is the risk weight of the zth prohibited item carried by the ith person, I i,＝ is the category feature information of the zth prohibited item carried by the ith person, N i is the total number of prohibited items carried by the i-th person, N x is the total number of contraband items of the xth suspected gang member, z≤N i , y≤N x , and z, y, N i and N x are all positive integers, D i is the risk factor of the i-th person, D x is the risk factor of the x-th suspected gang member, and C is the preset threshold.

[0081] According to an embodiment of the present invention, formula (3) includes the cosine similarity of the weighted category feature information of the yth prohibited item of the xth suspected gang member and the weighted category feature information of the zth prohibited item of the ith carrier: That is, the similarity between the yth prohibited item of the xth suspected gang member and the zth prohibited item of the ith carrier, wherein the weight of the weighted operation is the dangerousness weight. By weighting by the dangerousness weight, the distinction between the category feature information of different categories of prohibited items can be increased. It can represent the similarity between the yth prohibited item carried by the xth suspected gang member and the prohibited item with the greatest similarity among all the prohibited items carried by the ith carrier. It can be used to determine whether the yth prohibited item carried by the xth suspected gang member is of the same type as the prohibited item carried by the ith carrier. In theory, gang members not only have the same travel information, but also carry similar prohibited items. Therefore, the conditional function can be used. It means that when the similarity between the yth prohibited item carried by the xth suspected gang member and the prohibited item with the greatest similarity among all prohibited items carried by the ith carrier is greater than or equal to a preset threshold, the value of the conditional function is 1, otherwise it is 0, that is, the type of the yth prohibited item carried by the xth suspected gang member is the same as the type of prohibited item carried by the ith carrier. In other words, the xth suspected gang member and the ith carrier carry the same type of prohibited items.

[0082] therefore, It can represent the total number of prohibited items of the same category as those carried by the i-th person among the prohibited items carried by the x-th suspected gang member. Indicates the ratio of the total number of prohibited items of the same category as those carried by the i-th person in the prohibited items carried by the x-th suspected gang member to the total number of prohibited items carried by the x-th suspected gang member. The larger the ratio, the higher the proportion of carrying the same type of prohibited items, and the higher the possibility that the x-th suspected gang member and the i-th person to be tested form a gang.

[0083] According to an embodiment of the present invention, formula (3) also includes the difference D between the comprehensive risk coefficient of all prohibited items carried by the i-th person carrying the prohibited items and the comprehensive risk coefficient of all prohibited items carried by the x-th suspected gang member. i -D x ,therefore It can represent the relative difference between the comprehensive risk coefficient of all prohibited items carried by the ith carrier and the comprehensive risk coefficient of all prohibited items carried by the xth suspected gang member. Subtracting the above relative difference from 1 can obtain the similarity between the risk coefficient of the ith carrier and the risk of the prohibited items carried by the xth suspected gang member. The higher the similarity, the more similar the risk of the ith carrier is to the xth suspected gang member, that is, the two people may have the same purpose, etc.

[0084] According to an embodiment of the present invention, based on the above two aspects, the gang risk coefficient of the xth suspected gang member can be obtained. The larger the gang risk coefficient, the higher the similarity between the xth suspected gang member and the ith carrier, and the greater the possibility that the xth suspected gang member and the ith carrier form a gang.

[0085] According to an embodiment of the present invention, when the gang risk coefficient of the xth suspected gang member is greater than or equal to a preset gang risk coefficient threshold, that is, the xth suspected gang member is more likely to form a gang with the i-th carrier, the xth suspected gang member can be determined as a gang member.

[0086] According to the embodiment of the present invention, the above processing can be performed on each suspected gang member, so as to determine whether each suspected gang member is a gang member, and then the number of gang members, identity information, and category characteristic information of dangerous goods carried by each gang member can be recorded for inspection. If these people use dangerous goods to perform certain dangerous behaviors, the information of these gang members can be quickly queried through the above records.

[0087] In this way, the screening time interval can be determined based on the consistency of the gang members' travel time, and suspected gang members can be identified based on the consistency of the prohibited items carried by the gang members and the consistency of their dangerousness, thereby improving the accuracy of gang member screening, and then generating gang record information for easy inspection, thereby improving the comprehensiveness and accuracy of security checks.

[0088] According to the intelligent security inspection method of the embodiment of the present invention, after the suspected prohibited items are identified by the X-ray machine, the real image can be obtained by the camera, and the suspected prohibited items can be determined whether they are prohibited items according to the category feature information, size information and quantity of the suspected prohibited items, thereby reducing the possibility of misjudgment. In addition, the comprehensive risk coefficient of all prohibited items carried by the carrier can be determined, so as to determine the disposal method, thereby improving the comprehensiveness and accuracy of the security inspection and reducing safety hazards. When determining the comprehensive risk coefficient, the danger of the items carried by the carrier can be determined from multiple aspects such as cutting tools, dangerous solids, dangerous powders, dangerous liquids or dangerous gases and radioactive materials, and then the comprehensive risk coefficient of all prohibited items carried by the carrier can be determined, thereby improving the accuracy and objectivity of the comprehensive risk coefficient. Basic data is provided for determining the disposal method or generating alarm information. When disposing of prohibited items, the disposal method can be determined according to the comprehensive risk coefficient. If the disposal method is temporary storage, the prohibited items can be temporarily stored in a suitable locker, and the first facial feature information and the first signature image of the carrier can be obtained, thereby generating a temporary storage voucher printed with a pickup identification code. When picking up the item, the recipient scans the pickup identification code and compares the second facial feature information of the recipient with the first facial feature information to determine whether the person carrying the item is picking up the item. If the person carrying the item is picking up the item, the cabinet door is opened. If the person carrying the item is not picking up the item, the second signature image in the image of the authorization document signed by the person carrying the item held by the recipient can be photographed, and the first signature feature information and the second signature feature information can be compared to determine whether the authorization document can be used to pick up the item, thereby improving the accuracy and comprehensiveness of security checks, and improving the convenience and safety of storing and retrieving items. When checking gang members, the time interval for checking can be determined based on the consistency of the gang members' travel time, and suspected gang members can be identified based on the consistency of the prohibited items carried by the gang members and the consistency of the dangerousness, thereby improving the accuracy of checking gang members, and then gang record information can be generated for easy inspection, improving the comprehensiveness and accuracy of security checks.

[0089] Figure 2 A schematic diagram of an intelligent security inspection system according to an embodiment of the present invention is exemplarily shown, the system comprising: a camera, an ID card reader, a printer, a locker and a processor;

[0090] The processor is used to:

[0091] Get the detection time of the i-th person carrying security check, where i is a positive integer;

[0092] Obtain images of items to be inspected through an X-ray machine;

[0093] If it is determined that there are suspected prohibited items in the image to be inspected of the i-th person carrying the bag, the bag is opened for inspection and the real image of the suspected prohibited items is obtained through the camera;

[0094] Determining, by means of an image recognition model, category feature information of suspected prohibited items in the real image and size information of the suspected prohibited items;

[0095] Determining whether the suspected prohibited items are prohibited items based on the category feature information, size information and quantity of the suspected prohibited items;

[0096] If the suspected prohibited item is a prohibited item, determining the comprehensive risk factor of all prohibited items carried by the i-th carrier according to the category feature information, size information and quantity of the prohibited items;

[0097] Obtain the identity information of the i-th person through the ID card reader;

[0098] Determine a disposal method based on the identity information and the comprehensive risk factor;

[0099] The disposal methods include:

[0100] If the comprehensive risk factor is lower than or equal to a first threshold, the identity information, the category feature information of the prohibited item and the real image are saved;

[0101] If the comprehensive risk factor is higher than the first threshold and lower than or equal to the second threshold, the prohibited items are temporarily stored in a locker, a temporary storage certificate is generated according to the identity information, and the temporary storage certificate is printed by a printer, and the second threshold is higher than the first threshold;

[0102] If the comprehensive risk factor is higher than a second threshold, the prohibited items are stored in a locker and a prompt message is generated, wherein the prompt message is used to prompt the staff to call the police.

[0103] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent security inspection method, characterized in that: include: Get the detection time of the i-th person carrying security check, where i is a positive integer; Obtain images of items to be inspected through an X-ray machine; If it is determined that there are suspected prohibited items in the image to be inspected of the i-th person carrying the bag, the bag is opened for inspection and the real image of the suspected prohibited items is obtained through the camera; Determining, by means of an image recognition model, category feature information of suspected prohibited items in the real image and size information of the suspected prohibited items; Determining whether the suspected prohibited items are prohibited items based on the category feature information, size information and quantity of the suspected prohibited items; If the suspected prohibited item is a prohibited item, determining the comprehensive risk factor of all prohibited items carried by the i-th carrier according to the category feature information, size information and quantity of the prohibited items; Get the identity information of the i-th person; Determine a disposal method based on the identity information and the comprehensive risk factor; The method further comprises: If the risk factor is greater than or equal to the preset risk threshold, according to the formula [t c,i -ε(t d -t c,i ),t c,i +ε(t d -t c,i )], determine the troubleshooting time interval, where t c,i is the detection time of the security check of the i-th person, t d is the departure time of the vehicle, ε is a preset coefficient less than 1; Within the screening time interval, determine multiple suspected gang members whose travel information is consistent with the i-th person carrying the group; Determine the combined risk factor of all prohibited items carried by the suspected gang members; Determine the gang risk coefficient of the suspected gang member according to the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the i-th person to be tested, and the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the suspected gang member; In the case where the gang risk coefficient is greater than or equal to a preset coefficient threshold, determining the suspected gang member as a gang member; Generate gang record information based on the category feature information of the prohibited items carried by gang members; According to the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the i-th person to be tested, and the category characteristic information, risk weight and comprehensive risk coefficient of the prohibited items of the suspected gang members, the gang risk coefficient of the suspected gang members is determined, including: According to the formula Determine the gang risk coefficient G of the xth suspected gang member x , where α x，y is the risk weight of the yth prohibited item of the xth suspected gang member, I x，y is the category feature information of the yth prohibited item of the xth suspected gang member, α i，z is the risk weight of the zth prohibited item carried by the ith person, I i，z is the category feature information of the zth prohibited item carried by the ith person, N i is the total number of prohibited items carried by the i-th person, N x is the total number of contraband items of the xth suspected gang member, z≤N i , y≤N x , and z, y, N i and N x are all positive integers, D i is the risk factor of the i-th person, D x is the risk factor of the x-th suspected gang member, and C is the preset threshold.

2. The intelligent security inspection method according to claim 1, characterized in that: If the suspected prohibited item is a prohibited item, the comprehensive risk factor of all prohibited items carried by the i-th carrier is determined based on the category feature information, size information and quantity of the prohibited items, including: Determining a risk weight corresponding to the category of the j-th prohibited item of the i-th person carrying the j-th prohibited item according to the category feature information of the j-th prohibited item of the i-th person carrying the j-th prohibited item; The comprehensive risk coefficient of all prohibited items carried by the i-th carrier is determined according to the risk weight, the size information and the quantity.

3. The intelligent security inspection method according to claim 2, characterized in that: According to the hazard weight, the size information and the quantity, the comprehensive hazard coefficient of all prohibited items carried by the i-th carrier is determined, including: Determining whether the prohibited items include cutting tools according to the category feature information; If the prohibited items include cutting tools, obtaining the length of the cutting tools according to the size information of the cutting tools; Determining whether the prohibited items include dangerous goods containers according to the category characteristic information; If the prohibited items include a dangerous goods container, determine by means of a detector whether dangerous solids, dangerous powders, dangerous liquids or dangerous gases are stored in the dangerous goods container, and determine the concentration of the dangerous gases; Obtaining the capacity of the dangerous goods container according to the size information of the dangerous goods container; Determine the presence of radioactive substances in items through radiation detectors; If radiation is present, determining the radiation dose of the radiation; The comprehensive risk factor of all prohibited items carried by the i-th carrier is determined based on the number and length of the cutting tools, the number and capacity of dangerous goods containers containing dangerous solids, dangerous powders, dangerous liquids or dangerous gases, and the concentration of dangerous gases or dangerous liquids, as well as the number and radiation dose of radioactive materials.

4. The intelligent security inspection method according to claim 3, characterized in that: According to the number and length of the cutting tools, the number and capacity of dangerous goods containers containing dangerous solids, dangerous powders, dangerous liquids or dangerous gases, and the concentration of dangerous gases or dangerous liquids, as well as the number and radiation dose of radioactive materials, the comprehensive risk factor of all prohibited items carried by the i-th carrier is determined, including: According to the formula Determine the comprehensive risk factor D of all prohibited items carried by the i-th carrier i , where α i，j is the risk weight of the jth cutting tool of the i-th person carrying the tool, L i，j is the length of the jth blade of the i-th person carrying the i is the number of cutting tools of the i-th person carrying the knife, α i，k is the hazard weight of the kth hazardous container containing hazardous liquid or gas for the i-th person, V i，k is the volume of the kth dangerous goods container carrying the i-th person, C i，k is the concentration of dangerous liquid or gas in the kth dangerous goods container carrying the i-th person, m i is the number of dangerous goods containers containing dangerous liquids or gases for the i-th person carrying the dangerous goods, α i，s is the risk weight of the sth radiation of the ith person, D i，s is the radiation dose of the sth radiation object carrying the ith person, h i is the number of radioactive materials carrying the i-th person, j≤n i , k≤m i ,s≤h i , and j, k, s, n i 、m i and h i All are positive integers.

5. The intelligent security inspection method according to claim 1, characterized in that: Determine the disposal method according to the identity information and the comprehensive risk factor, including: If the comprehensive risk factor is lower than or equal to a first threshold, the identity information, the category feature information of the prohibited item and the real image are saved; If the comprehensive risk factor is higher than a first threshold value and lower than or equal to a second threshold value, the prohibited items are temporarily stored in a locker and a temporary storage certificate is generated according to the identity information, and the second threshold value is higher than the first threshold value; If the comprehensive risk factor is higher than a second threshold, the prohibited items are stored in a locker and a prompt message is generated, wherein the prompt message is used to prompt the staff to call the police.

6. The intelligent security inspection method according to claim 5, characterized in that: If the comprehensive risk factor is higher than the first threshold and lower than or equal to the second threshold, the prohibited items are temporarily stored in a locker and a temporary storage certificate is generated according to the identity information, including: Acquire the identity information of the carrier, and acquire the facial image and the first signature image of the carrier; Determine a locker for temporarily storing prohibited items according to the size information and quantity of the prohibited items, and open the locker; After the prohibited items are stored in the locker, the locker is closed, a pickup code is generated, and a temporary storage voucher is printed. The content of the temporary storage voucher includes the pickup code and a pickup time limit. After the pickup time limit, the pickup code becomes invalid.

7. The intelligent security inspection method according to claim 6, characterized in that: The method further comprises: Scan the pickup identification code of the temporary voucher and obtain the pickup time limit; If the current date is before the stated collection time limit, a facial image of the recipient is captured; Acquire first facial feature information of the facial image of the carrier and second facial feature information of the facial image of the recipient; If the similarity between the first facial feature information and the second facial feature information is greater than or equal to a preset facial similarity threshold, opening the locker; If the similarity between the first facial feature information and the second facial feature information is less than a preset facial similarity threshold, photographing an image of the entrusted pickup document with the signature of the carrier, and intercepting a second signature image at a preset position in the image of the entrusted pickup document; Acquire first signature feature information of the first signature image and second signature feature information of the second signature image; If the first signature feature information and the second signature feature information are greater than or equal to a preset signature similarity threshold, the locker is opened.

8. An intelligent security inspection system for executing the intelligent security inspection method according to any one of claims 1 to 7, characterized in that: include: cameras, ID card readers, printers, lockers and processors; The processor is used to: Get the detection time of the i-th person carrying security check, where i is a positive integer; Obtain images of items to be inspected through an X-ray machine; If it is determined that there are suspected prohibited items in the image to be inspected of the i-th person carrying the bag, the bag is opened for inspection and the real image of the suspected prohibited items is obtained through the camera; Determining, by means of an image recognition model, category feature information of suspected prohibited items in the real image and size information of the suspected prohibited items; Determining whether the suspected prohibited items are prohibited items based on the category feature information, size information and quantity of the suspected prohibited items; If the suspected prohibited item is a prohibited item, determining the comprehensive risk factor of all prohibited items carried by the i-th carrier according to the category feature information, size information and quantity of the prohibited items; Obtain the identity information of the i-th person through the ID card reader; Determine a disposal method based on the identity information and the comprehensive risk factor; The disposal methods include: If the comprehensive risk factor is lower than or equal to a first threshold, the identity information, the category feature information of the prohibited item and the real image are saved; If the comprehensive risk factor is higher than the first threshold and lower than or equal to the second threshold, the prohibited items are temporarily stored in a locker, a temporary storage certificate is generated according to the identity information, and the temporary storage certificate is printed by a printer, and the second threshold is higher than the first threshold; If the comprehensive risk factor is higher than a second threshold, the prohibited items are stored in a locker and a prompt message is generated, wherein the prompt message is used to prompt the staff to call the police.

Images